基于对抗性扰动图形神经网络的隐私攻击防御策略

为了保护隐私,同时维护干扰数据效用,提出了一种基于对抗性扰动图形神经网络的隐私攻击防御策略。候选边缘选择确保扰动图不可见,图形神经网络组合优化,确保隐私得到保护和数据实用性。进一步证明扰动图结构比扰动节点特征对图形神经网络的影响更大,并且证明扰动可以在模型不可察觉性和隐私保护之间取得平衡。实验结果表明:提出方法可以同时保持图形数据的不可见性,保持目标标签分类的预测置信度并降低隐私标签分类的预测置信度。

Water quality forecast through application of BP neural network at Yuqiao reservoir

This paper deals with the study of a water quality forecast model through application of BP neural network technique and GUI (Graphical User Interfaces) function of MATLAB at Yuqiao reservoir in Tianjin. To overcome the shortcomings of traditional BP algorithm as being slow to converge and easy to reach extreme minimum value,the model adopts LM (Leven-berg-Marquardt) algorithm to achieve a higher speed and a lower error rate. When factors affecting the study object are identified,the reservoir's 2005 measured values are used as sample data to test the model. The number of neurons and the type of transfer functions in the hidden layer of the neural network are changed from time to time to achieve the best forecast results. Through simulation testing the model shows high efficiency in forecasting the water quality of the reservoir.

Optoelectronic Detecting System for Inner Walls of Pipes

This paper is concerned with a high characteristic image processing and recognition system that is used for inspecting real-time blemishes, streaks and cracks on the inner walls of high accuracy pipes. As a regular detector, the BP neural network is used for extracting features of the image inspected and classifying these images, it takes fully advantage of the function of artificial neural network, such as the information distributed memory, large scale self-adapting parallel processing, high fault-tolerant ability and so forth. Besides, an improved BP algorithm is used in the system for training the network, and making the learning procedure of the net converges to the minimum of overall situation at high rate.

Flame image recognition of alumina rotary kiln by artificial neural network and support vector machine methods

Based on the Fourier transform, a new shape descriptor was proposed to represent the flame image. By employing the shape descriptor as the input, the flame image recognition was studied by the methods of the artificial neural network(ANN) and the support vector machine(SVM) respectively. And the recognition experiments were carried out by using flame image data sampled from an alumina rotary kiln to evaluate their effectiveness. The results show that the two recognition methods can achieve good results, which verify the effectiveness of the shape descriptor. The highest recognition rate is 88.83% for SVM and 87.38% for ANN, which means that the performance of the SVM is better than that of the ANN.

Image mathematical morphology and image restoration application in detecting underground bin level

By using image recognition technology, the underground bin level can be detdcted. The bin image is noised by vibration, atomy, backgroun and so on. The image restoration and image mathematical morphology were used based on neural network. A modified Hopfield network was presented for image restoration. The greed algorithm with n-simultaneous updates and apartially asynchronous algorithm were combined, im- proving convergence and avoiding synchronization penalties. Mathematical morphology was widely applicated in digital image processing. The basic idea of mathematical mor- phology is to use construction element measure image morphology for solving under- stand problem. Presented advanced Cellular neural network that forms MMCNN equa- tion to be suit for mathematical morphology filter. It gave the theory of MMCNN dynamic extent and stable state. It was evidenced that arrived mathematical morphology filter through steady of dynamic precess in definite condition. The results of implementation were applied in detecting undergroug bin level.

Storage capacity of complex Hopfield model

The Dirac symbol is used to represent the discrete complex Hopfield neural network model.The signal-to-noise theory and the computer numerical solution are made to analyse the storage capacity of the model.The storage capacity ratio of the model equals to that of the Hopfield model.Finally,using the model to recognize the 4-level grey or color patterns is discussed.

An experimental investigation into electromyography, constitutive relationship and morphology of crucian carp for biomechanical “digital fish”

Currently, the integrated biomechanical studies on fish locomotion come into focus, so it is urgent to provide reliable and sys- tematic experimental results, and to establish a biomechanical ＂digital fish＂ database for some typical fish species. Accord- ingly, based on the control framework of ＂Neural Control - Active Contraction of Muscle - Passive Deformation＂, the elec- tromyography （EMG） signals, the mechanical properties and the constitutive relationship of skin, muscle, and body trunk, as well as morphological parameters of crucian carp, are investigated with experiments, from which a simplified database of bio- mechanical ＂digital fish＂ is established. First, the EMG signals from three lateral superficial red muscles of crucian carp, which was evolving in the C-start movement, were acquired with a self-designing amplifier. The modes of muscle activity were also investigated. Secondly, the Young＇s modulus and the reduced relaxation function of crucian carp＇s skin and muscle were de- termined by failure tests and relaxation tests in uniaxial tensile ways, respectively. Viscoelastic models were adopted to deduce the constitutive relationship. The mechanical properties and the angular stiffness of different sites on the crucian carp＇s body trunk were obtained with dynamic bending experiments, where a self-designing dynamic bending test machine was employed. The conclusion was drawn regarding the body trunk of crucian carp under dynamic bending deformation as an approximate elastomer. According to the above experimental results, a possible benefit of body effective stiffness increasing with a little energy dissipation was discussed. Thirdly, the distribution of geometric parameters and weight parameters for a single experi- mental individual and multiple individuals of crucian carp was studied with experiments. Finally, considering all the above re- suits, generic experimental data were obtained by normalization, and a preliminary biomechanical ＂digital fish＂ database for crucian carp was established.